跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.18035 · v1

RL$^{\mathrm{RT}}$: On-Device Reinforcement Learning Runtime

首次提交 2026-11-13 19:05
版本更新 2026-11-13 19:05
雷达观测 2026-11-16 11:42
arXiv ↗PDF ↗

摘要

On-device reinforcement learning runs a periodic actor and a learner on one embedded GPU shared with other workloads. Because the learner produces the actor's weights, existing designs stall the actor or let its policy drift. We present RLRT^{\mathrm{RT}}, an on-device runtime that makes this coupling a tunable parameter: a refresh bound limits actor releases between refreshes, and a GPU permit with slack-aware admission prioritises the actor and fills spare time with training atop any base scheduler. Under the real refresh cost on two Jetson boards, RLRT^{\mathrm{RT}} keeps a 16.8 M-parameter policy's deadline misses below 1%, against 85 to 100% without it.

作者备注:8 pages, 11 figures

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-13 19:05 · 最新观测版本

RL$^{\mathrm{RT}}$: On-Device Reinforcement Learning Runtime

On-device reinforcement learning runs a periodic actor and a learner on one embedded GPU shared with other workloads. Because the learner produces the actor's weights, existing designs stall the actor or let its policy drift. We present RLRT^{\mathrm{RT}}, an on-device runtime that makes this coupling a tunable parameter: a refresh bound limits actor releases between refreshes, and a GPU permit with slack-aware admission prioritises the actor and fills spare time with training atop any base scheduler. Under the real refresh cost on two Jetson boards, RLRT^{\mathrm{RT}} keeps a 16.8 M-parameter policy's deadline misses below 1%, against 85 to 100% without it.

查看此版本解读 →查看此版本原文 ↗